Graceful Sentence Recognition Based On Lexical Features and CNN-Att-BiGRU
Zhiheng Wang, Fang Wang, Shucheng Huang · 2022
In this paper, we propose a graceful sentence recognition model based on lexical features and CNN-Att-BiGRU. Firstly, the lexical items in the sentences and the lexical features corresponding to each lexical item are vectorized and fused to represent them; secondly, a convolutional neural network (CNN) introducing Attention Mechanisms is used to obtain the local features of the fused word vectors; a bi-directional gated recurrent unit (BiGRU) is used to serialize the local features to represent them to obtain the global features; finally, they are connected to the Softmax classifier for graceful sentence recognition. Experiments show that the graceful sentence recognition model based on CNN-Att-BiGRU has the highest recognition precision of graceful sentences, reaching 89.46%, with an F1 value of 82.38%. After adding the fused word vector, the F1 value improved by 0.67.